Using the Tools of Cognitive Science to Understand Large Language Models at Different Levels of Analysis

• URL: http://arxiv.org/abs/2503.13401v1
• Date: Mon, 17 Mar 2025 17:33:54 GMT
• Title: Using the Tools of Cognitive Science to Understand Large Language Models at Different Levels of Analysis
• Authors: Alexander Ku, Declan Campbell, Xuechunzi Bai, Jiayi Geng, Ryan Liu, Raja Marjieh, R. Thomas McCoy, Andrew Nam, Ilia Sucholutsky, Veniamin Veselovsky, Liyi Zhang, Jian-Qiao Zhu, Thomas L. Griffiths,
• Abstract summary: We argue that methods developed in cognitive science can be useful for understanding large language models.<n>We propose a framework for applying these methods based on Marr's three levels of analysis.
• Score: 46.08309259203833
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to the historical difficulties in understanding the human mind, we argue that methods developed in cognitive science can be useful for understanding large language models. We propose a framework for applying these methods based on Marr's three levels of analysis. By revisiting established cognitive science techniques relevant to each level and illustrating their potential to yield insights into the behavior and internal organization of large language models, we aim to provide a toolkit for making sense of these new kinds of minds.

Related papers

• The Philosophical Foundations of Growing AI Like A Child [0.0]
  This paper argues that both challenges stem from a core discrepancy between human and machine cognitive development.<n>It explores empirical evidence of core knowledge in humans, analyzes why language models fail to acquire it, and argues that this limitation is not an inherent architectural constraint.
  arXiv  Detail & Related papers  (2025-02-15T09:47:20Z)
• Language Evolution with Deep Learning [49.879239655532324]
  Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language. This chapter explores another class of computational models that have recently revolutionized the field of machine learning: deep learning models.
  arXiv  Detail & Related papers  (2024-03-18T16:52:54Z)
• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning [0.0]
  We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses. Brain-inspired cognition methods use computational models that mimic the human mind to enhance intelligent behavior in artificial agents and autonomous robots.
  arXiv  Detail & Related papers  (2024-03-11T18:11:00Z)
• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• Exploiting Language Models as a Source of Knowledge for Cognitive Agents [4.557963624437782]
  Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems, our research is exploiting language models as a source of task knowledge for cognitive agents, that is, agents realized via a cognitive architecture.
  arXiv  Detail & Related papers  (2023-09-05T15:18:04Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• Language Cognition and Language Computation -- Human and Machine Language Understanding [51.56546543716759]
  Language understanding is a key scientific issue in the fields of cognitive and computer science. Can a combination of the disciplines offer new insights for building intelligent language models?
  arXiv  Detail & Related papers  (2023-01-12T02:37:00Z)
• The Debate Over Understanding in AI's Large Language Models [0.18275108630751835]
  We survey a current, heated debate in the AI research community on whether large pre-trained language models can be said to "understand" language. We argue that a new science of intelligence can be developed that will provide insight into distinct modes of understanding.
  arXiv  Detail & Related papers  (2022-10-14T17:04:29Z)
• Language Models as a Knowledge Source for Cognitive Agents [9.061356032792954]
  Language models (LMs) are sentence-completion engines trained on massive corpora. This paper outlines the challenges and opportunities for using language models as a new knowledge source for cognitive systems. It also identifies possible ways to improve knowledge extraction from language models using the capabilities provided by cognitive systems.
  arXiv  Detail & Related papers  (2021-09-17T01:12:34Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.